From cf4ce59b3b70238352c7f1729f0f7223214828ad Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 20 Sep 2024 01:46:19 +0000
Subject: [PATCH] rtl88x2CE_WiFi_linux add concurrent mode
---
kernel/arch/powerpc/kernel/process.c | 768 +++++++++++++++++++++++++++++++++-------------------------
1 files changed, 438 insertions(+), 330 deletions(-)
diff --git a/kernel/arch/powerpc/kernel/process.c b/kernel/arch/powerpc/kernel/process.c
index 02b69a6..cf375d6 100644
--- a/kernel/arch/powerpc/kernel/process.c
+++ b/kernel/arch/powerpc/kernel/process.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Derived from "arch/i386/kernel/process.c"
* Copyright (C) 1995 Linus Torvalds
@@ -7,11 +8,6 @@
*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#include <linux/errno.h>
@@ -43,8 +39,8 @@
#include <linux/uaccess.h>
#include <linux/elf-randomize.h>
#include <linux/pkeys.h>
+#include <linux/seq_buf.h>
-#include <asm/pgtable.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/mmu.h>
@@ -65,6 +61,8 @@
#include <asm/livepatch.h>
#include <asm/cpu_has_feature.h>
#include <asm/asm-prototypes.h>
+#include <asm/stacktrace.h>
+#include <asm/hw_breakpoint.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
@@ -118,17 +116,16 @@
}
early_param("ppc_strict_facility_enable", enable_strict_msr_control);
-unsigned long msr_check_and_set(unsigned long bits)
+/* notrace because it's called by restore_math */
+unsigned long notrace msr_check_and_set(unsigned long bits)
{
unsigned long oldmsr = mfmsr();
unsigned long newmsr;
newmsr = oldmsr | bits;
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
newmsr |= MSR_VSX;
-#endif
if (oldmsr != newmsr)
mtmsr_isync(newmsr);
@@ -137,17 +134,16 @@
}
EXPORT_SYMBOL_GPL(msr_check_and_set);
-void __msr_check_and_clear(unsigned long bits)
+/* notrace because it's called by restore_math */
+void notrace __msr_check_and_clear(unsigned long bits)
{
unsigned long oldmsr = mfmsr();
unsigned long newmsr;
newmsr = oldmsr & ~bits;
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
newmsr &= ~MSR_VSX;
-#endif
if (oldmsr != newmsr)
mtmsr_isync(newmsr);
@@ -162,10 +158,8 @@
save_fpu(tsk);
msr = tsk->thread.regs->msr;
msr &= ~(MSR_FP|MSR_FE0|MSR_FE1);
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX))
msr &= ~MSR_VSX;
-#endif
tsk->thread.regs->msr = msr;
}
@@ -235,23 +229,11 @@
}
}
EXPORT_SYMBOL(enable_kernel_fp);
-
-static int restore_fp(struct task_struct *tsk)
-{
- if (tsk->thread.load_fp) {
- load_fp_state(¤t->thread.fp_state);
- current->thread.load_fp++;
- return 1;
- }
- return 0;
-}
#else
-static int restore_fp(struct task_struct *tsk) { return 0; }
+static inline void __giveup_fpu(struct task_struct *tsk) { }
#endif /* CONFIG_PPC_FPU */
#ifdef CONFIG_ALTIVEC
-#define loadvec(thr) ((thr).load_vec)
-
static void __giveup_altivec(struct task_struct *tsk)
{
unsigned long msr;
@@ -259,10 +241,8 @@
save_altivec(tsk);
msr = tsk->thread.regs->msr;
msr &= ~MSR_VEC;
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX))
msr &= ~MSR_VSX;
-#endif
tsk->thread.regs->msr = msr;
}
@@ -317,21 +297,6 @@
}
}
EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
-
-static int restore_altivec(struct task_struct *tsk)
-{
- if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
- load_vr_state(&tsk->thread.vr_state);
- tsk->thread.used_vr = 1;
- tsk->thread.load_vec++;
-
- return 1;
- }
- return 0;
-}
-#else
-#define loadvec(thr) 0
-static inline int restore_altivec(struct task_struct *tsk) { return 0; }
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
@@ -399,18 +364,6 @@
}
}
EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
-
-static int restore_vsx(struct task_struct *tsk)
-{
- if (cpu_has_feature(CPU_FTR_VSX)) {
- tsk->thread.used_vsr = 1;
- return 1;
- }
-
- return 0;
-}
-#else
-static inline int restore_vsx(struct task_struct *tsk) { return 0; }
#endif /* CONFIG_VSX */
#ifdef CONFIG_SPE
@@ -455,21 +408,14 @@
static int __init init_msr_all_available(void)
{
-#ifdef CONFIG_PPC_FPU
- msr_all_available |= MSR_FP;
-#endif
-#ifdef CONFIG_ALTIVEC
+ if (IS_ENABLED(CONFIG_PPC_FPU))
+ msr_all_available |= MSR_FP;
if (cpu_has_feature(CPU_FTR_ALTIVEC))
msr_all_available |= MSR_VEC;
-#endif
-#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX))
msr_all_available |= MSR_VSX;
-#endif
-#ifdef CONFIG_SPE
if (cpu_has_feature(CPU_FTR_SPE))
msr_all_available |= MSR_SPE;
-#endif
return 0;
}
@@ -493,53 +439,129 @@
WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
-#ifdef CONFIG_PPC_FPU
if (usermsr & MSR_FP)
__giveup_fpu(tsk);
-#endif
-#ifdef CONFIG_ALTIVEC
if (usermsr & MSR_VEC)
__giveup_altivec(tsk);
-#endif
-#ifdef CONFIG_SPE
if (usermsr & MSR_SPE)
__giveup_spe(tsk);
-#endif
msr_check_and_clear(msr_all_available);
}
EXPORT_SYMBOL(giveup_all);
-void restore_math(struct pt_regs *regs)
+#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC_FPU
+static bool should_restore_fp(void)
+{
+ if (current->thread.load_fp) {
+ current->thread.load_fp++;
+ return true;
+ }
+ return false;
+}
+
+static void do_restore_fp(void)
+{
+ load_fp_state(¤t->thread.fp_state);
+}
+#else
+static bool should_restore_fp(void) { return false; }
+static void do_restore_fp(void) { }
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static bool should_restore_altivec(void)
+{
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) && (current->thread.load_vec)) {
+ current->thread.load_vec++;
+ return true;
+ }
+ return false;
+}
+
+static void do_restore_altivec(void)
+{
+ load_vr_state(¤t->thread.vr_state);
+ current->thread.used_vr = 1;
+}
+#else
+static bool should_restore_altivec(void) { return false; }
+static void do_restore_altivec(void) { }
+#endif /* CONFIG_ALTIVEC */
+
+static bool should_restore_vsx(void)
+{
+ if (cpu_has_feature(CPU_FTR_VSX))
+ return true;
+ return false;
+}
+#ifdef CONFIG_VSX
+static void do_restore_vsx(void)
+{
+ current->thread.used_vsr = 1;
+}
+#else
+static void do_restore_vsx(void) { }
+#endif /* CONFIG_VSX */
+
+/*
+ * The exception exit path calls restore_math() with interrupts hard disabled
+ * but the soft irq state not "reconciled". ftrace code that calls
+ * local_irq_save/restore causes warnings.
+ *
+ * Rather than complicate the exit path, just don't trace restore_math. This
+ * could be done by having ftrace entry code check for this un-reconciled
+ * condition where MSR[EE]=0 and PACA_IRQ_HARD_DIS is not set, and
+ * temporarily fix it up for the duration of the ftrace call.
+ */
+void notrace restore_math(struct pt_regs *regs)
{
unsigned long msr;
-
- if (!MSR_TM_ACTIVE(regs->msr) &&
- !current->thread.load_fp && !loadvec(current->thread))
- return;
+ unsigned long new_msr = 0;
msr = regs->msr;
- msr_check_and_set(msr_all_available);
/*
- * Only reload if the bit is not set in the user MSR, the bit BEING set
- * indicates that the registers are hot
+ * new_msr tracks the facilities that are to be restored. Only reload
+ * if the bit is not set in the user MSR (if it is set, the registers
+ * are live for the user thread).
*/
- if ((!(msr & MSR_FP)) && restore_fp(current))
- msr |= MSR_FP | current->thread.fpexc_mode;
+ if ((!(msr & MSR_FP)) && should_restore_fp())
+ new_msr |= MSR_FP;
- if ((!(msr & MSR_VEC)) && restore_altivec(current))
- msr |= MSR_VEC;
+ if ((!(msr & MSR_VEC)) && should_restore_altivec())
+ new_msr |= MSR_VEC;
- if ((msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC) &&
- restore_vsx(current)) {
- msr |= MSR_VSX;
+ if ((!(msr & MSR_VSX)) && should_restore_vsx()) {
+ if (((msr | new_msr) & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC))
+ new_msr |= MSR_VSX;
}
- msr_check_and_clear(msr_all_available);
+ if (new_msr) {
+ unsigned long fpexc_mode = 0;
- regs->msr = msr;
+ msr_check_and_set(new_msr);
+
+ if (new_msr & MSR_FP) {
+ do_restore_fp();
+
+ // This also covers VSX, because VSX implies FP
+ fpexc_mode = current->thread.fpexc_mode;
+ }
+
+ if (new_msr & MSR_VEC)
+ do_restore_altivec();
+
+ if (new_msr & MSR_VSX)
+ do_restore_vsx();
+
+ msr_check_and_clear(new_msr);
+
+ regs->msr |= new_msr | fpexc_mode;
+ }
}
+#endif /* CONFIG_PPC_BOOK3S_64 */
static void save_all(struct task_struct *tsk)
{
@@ -600,11 +622,47 @@
(void __user *)address);
}
#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
+
+static void do_break_handler(struct pt_regs *regs)
+{
+ struct arch_hw_breakpoint null_brk = {0};
+ struct arch_hw_breakpoint *info;
+ struct ppc_inst instr = ppc_inst(0);
+ int type = 0;
+ int size = 0;
+ unsigned long ea;
+ int i;
+
+ /*
+ * If underneath hw supports only one watchpoint, we know it
+ * caused exception. 8xx also falls into this category.
+ */
+ if (nr_wp_slots() == 1) {
+ __set_breakpoint(0, &null_brk);
+ current->thread.hw_brk[0] = null_brk;
+ current->thread.hw_brk[0].flags |= HW_BRK_FLAG_DISABLED;
+ return;
+ }
+
+ /* Otherwise findout which DAWR caused exception and disable it. */
+ wp_get_instr_detail(regs, &instr, &type, &size, &ea);
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ info = ¤t->thread.hw_brk[i];
+ if (!info->address)
+ continue;
+
+ if (wp_check_constraints(regs, instr, ea, type, size, info)) {
+ __set_breakpoint(i, &null_brk);
+ current->thread.hw_brk[i] = null_brk;
+ current->thread.hw_brk[i].flags |= HW_BRK_FLAG_DISABLED;
+ }
+ }
+}
+
void do_break (struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
- siginfo_t info;
-
current->thread.trap_nr = TRAP_HWBKPT;
if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
11, SIGSEGV) == NOTIFY_STOP)
@@ -613,20 +671,22 @@
if (debugger_break_match(regs))
return;
- /* Clear the breakpoint */
- hw_breakpoint_disable();
+ /*
+ * We reach here only when watchpoint exception is generated by ptrace
+ * event (or hw is buggy!). Now if CONFIG_HAVE_HW_BREAKPOINT is set,
+ * watchpoint is already handled by hw_breakpoint_handler() so we don't
+ * have to do anything. But when CONFIG_HAVE_HW_BREAKPOINT is not set,
+ * we need to manually handle the watchpoint here.
+ */
+ if (!IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT))
+ do_break_handler(regs);
/* Deliver the signal to userspace */
- clear_siginfo(&info);
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_HWBKPT;
- info.si_addr = (void __user *)address;
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address);
}
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-static DEFINE_PER_CPU(struct arch_hw_breakpoint, current_brk);
+static DEFINE_PER_CPU(struct arch_hw_breakpoint, current_brk[HBP_NUM_MAX]);
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
/*
@@ -700,19 +760,49 @@
EXPORT_SYMBOL_GPL(switch_booke_debug_regs);
#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
#ifndef CONFIG_HAVE_HW_BREAKPOINT
-static void set_breakpoint(struct arch_hw_breakpoint *brk)
+static void set_breakpoint(int i, struct arch_hw_breakpoint *brk)
{
preempt_disable();
- __set_breakpoint(brk);
+ __set_breakpoint(i, brk);
preempt_enable();
}
static void set_debug_reg_defaults(struct thread_struct *thread)
{
- thread->hw_brk.address = 0;
- thread->hw_brk.type = 0;
- if (ppc_breakpoint_available())
- set_breakpoint(&thread->hw_brk);
+ int i;
+ struct arch_hw_breakpoint null_brk = {0};
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ thread->hw_brk[i] = null_brk;
+ if (ppc_breakpoint_available())
+ set_breakpoint(i, &thread->hw_brk[i]);
+ }
+}
+
+static inline bool hw_brk_match(struct arch_hw_breakpoint *a,
+ struct arch_hw_breakpoint *b)
+{
+ if (a->address != b->address)
+ return false;
+ if (a->type != b->type)
+ return false;
+ if (a->len != b->len)
+ return false;
+ /* no need to check hw_len. it's calculated from address and len */
+ return true;
+}
+
+static void switch_hw_breakpoint(struct task_struct *new)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (likely(hw_brk_match(this_cpu_ptr(¤t_brk[i]),
+ &new->thread.hw_brk[i])))
+ continue;
+
+ __set_breakpoint(i, &new->thread.hw_brk[i]);
+ }
}
#endif /* !CONFIG_HAVE_HW_BREAKPOINT */
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
@@ -721,9 +811,8 @@
static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
{
mtspr(SPRN_DAC1, dabr);
-#ifdef CONFIG_PPC_47x
- isync();
-#endif
+ if (IS_ENABLED(CONFIG_PPC_47x))
+ isync();
return 0;
}
#elif defined(CONFIG_PPC_BOOK3S)
@@ -732,28 +821,6 @@
mtspr(SPRN_DABR, dabr);
if (cpu_has_feature(CPU_FTR_DABRX))
mtspr(SPRN_DABRX, dabrx);
- return 0;
-}
-#elif defined(CONFIG_PPC_8xx)
-static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
-{
- unsigned long addr = dabr & ~HW_BRK_TYPE_DABR;
- unsigned long lctrl1 = 0x90000000; /* compare type: equal on E & F */
- unsigned long lctrl2 = 0x8e000002; /* watchpoint 1 on cmp E | F */
-
- if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
- lctrl1 |= 0xa0000;
- else if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
- lctrl1 |= 0xf0000;
- else if ((dabr & HW_BRK_TYPE_RDWR) == 0)
- lctrl2 = 0;
-
- mtspr(SPRN_LCTRL2, 0);
- mtspr(SPRN_CMPE, addr);
- mtspr(SPRN_CMPF, addr + 4);
- mtspr(SPRN_LCTRL1, lctrl1);
- mtspr(SPRN_LCTRL2, lctrl2);
-
return 0;
}
#else
@@ -776,41 +843,48 @@
return __set_dabr(dabr, dabrx);
}
-static inline int set_dawr(struct arch_hw_breakpoint *brk)
+static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
{
- unsigned long dawr, dawrx, mrd;
+ unsigned long lctrl1 = LCTRL1_CTE_GT | LCTRL1_CTF_LT | LCTRL1_CRWE_RW |
+ LCTRL1_CRWF_RW;
+ unsigned long lctrl2 = LCTRL2_LW0EN | LCTRL2_LW0LADC | LCTRL2_SLW0EN;
+ unsigned long start_addr = ALIGN_DOWN(brk->address, HW_BREAKPOINT_SIZE);
+ unsigned long end_addr = ALIGN(brk->address + brk->len, HW_BREAKPOINT_SIZE);
- dawr = brk->address;
+ if (start_addr == 0)
+ lctrl2 |= LCTRL2_LW0LA_F;
+ else if (end_addr == 0)
+ lctrl2 |= LCTRL2_LW0LA_E;
+ else
+ lctrl2 |= LCTRL2_LW0LA_EandF;
- dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) \
- << (63 - 58); //* read/write bits */
- dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) \
- << (63 - 59); //* translate */
- dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) \
- >> 3; //* PRIM bits */
- /* dawr length is stored in field MDR bits 48:53. Matches range in
- doublewords (64 bits) baised by -1 eg. 0b000000=1DW and
- 0b111111=64DW.
- brk->len is in bytes.
- This aligns up to double word size, shifts and does the bias.
- */
- mrd = ((brk->len + 7) >> 3) - 1;
- dawrx |= (mrd & 0x3f) << (63 - 53);
+ mtspr(SPRN_LCTRL2, 0);
- if (ppc_md.set_dawr)
- return ppc_md.set_dawr(dawr, dawrx);
- mtspr(SPRN_DAWR, dawr);
- mtspr(SPRN_DAWRX, dawrx);
+ if ((brk->type & HW_BRK_TYPE_RDWR) == 0)
+ return 0;
+
+ if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
+ lctrl1 |= LCTRL1_CRWE_RO | LCTRL1_CRWF_RO;
+ if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
+ lctrl1 |= LCTRL1_CRWE_WO | LCTRL1_CRWF_WO;
+
+ mtspr(SPRN_CMPE, start_addr - 1);
+ mtspr(SPRN_CMPF, end_addr);
+ mtspr(SPRN_LCTRL1, lctrl1);
+ mtspr(SPRN_LCTRL2, lctrl2);
+
return 0;
}
-void __set_breakpoint(struct arch_hw_breakpoint *brk)
+void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk)
{
- memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk));
+ memcpy(this_cpu_ptr(¤t_brk[nr]), brk, sizeof(*brk));
- if (cpu_has_feature(CPU_FTR_DAWR))
+ if (dawr_enabled())
// Power8 or later
- set_dawr(brk);
+ set_dawr(nr, brk);
+ else if (IS_ENABLED(CONFIG_PPC_8xx))
+ set_breakpoint_8xx(brk);
else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
// Power7 or earlier
set_dabr(brk);
@@ -822,26 +896,14 @@
/* Check if we have DAWR or DABR hardware */
bool ppc_breakpoint_available(void)
{
- if (cpu_has_feature(CPU_FTR_DAWR))
- return true; /* POWER8 DAWR */
+ if (dawr_enabled())
+ return true; /* POWER8 DAWR or POWER9 forced DAWR */
if (cpu_has_feature(CPU_FTR_ARCH_207S))
return false; /* POWER9 with DAWR disabled */
/* DABR: Everything but POWER8 and POWER9 */
return true;
}
EXPORT_SYMBOL_GPL(ppc_breakpoint_available);
-
-static inline bool hw_brk_match(struct arch_hw_breakpoint *a,
- struct arch_hw_breakpoint *b)
-{
- if (a->address != b->address)
- return false;
- if (a->type != b->type)
- return false;
- if (a->len != b->len)
- return false;
- return true;
-}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1143,11 +1205,6 @@
thread_pkey_regs_restore(new_thread, old_thread);
}
-#ifdef CONFIG_PPC_BOOK3S_64
-#define CP_SIZE 128
-static const u8 dummy_copy_buffer[CP_SIZE] __attribute__((aligned(CP_SIZE)));
-#endif
-
struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *new)
{
@@ -1170,6 +1227,19 @@
__flush_tlb_pending(batch);
batch->active = 0;
}
+
+ /*
+ * On POWER9 the copy-paste buffer can only paste into
+ * foreign real addresses, so unprivileged processes can not
+ * see the data or use it in any way unless they have
+ * foreign real mappings. If the new process has the foreign
+ * real address mappings, we must issue a cp_abort to clear
+ * any state and prevent snooping, corruption or a covert
+ * channel. ISA v3.1 supports paste into local memory.
+ */
+ if (new->mm && (cpu_has_feature(CPU_FTR_ARCH_31) ||
+ atomic_read(&new->mm->context.vas_windows)))
+ asm volatile(PPC_CP_ABORT);
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -1180,8 +1250,7 @@
* schedule DABR
*/
#ifndef CONFIG_HAVE_HW_BREAKPOINT
- if (unlikely(!hw_brk_match(this_cpu_ptr(¤t_brk), &new->thread.hw_brk)))
- __set_breakpoint(&new->thread.hw_brk);
+ switch_hw_breakpoint(new);
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
#endif
@@ -1216,61 +1285,68 @@
last = _switch(old_thread, new_thread);
+ /*
+ * Nothing after _switch will be run for newly created tasks,
+ * because they switch directly to ret_from_fork/ret_from_kernel_thread
+ * etc. Code added here should have a comment explaining why that is
+ * okay.
+ */
+
#ifdef CONFIG_PPC_BOOK3S_64
+ /*
+ * This applies to a process that was context switched while inside
+ * arch_enter_lazy_mmu_mode(), to re-activate the batch that was
+ * deactivated above, before _switch(). This will never be the case
+ * for new tasks.
+ */
if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
batch = this_cpu_ptr(&ppc64_tlb_batch);
batch->active = 1;
}
- if (current_thread_info()->task->thread.regs) {
- restore_math(current_thread_info()->task->thread.regs);
-
- /*
- * The copy-paste buffer can only store into foreign real
- * addresses, so unprivileged processes can not see the
- * data or use it in any way unless they have foreign real
- * mappings. If the new process has the foreign real address
- * mappings, we must issue a cp_abort to clear any state and
- * prevent snooping, corruption or a covert channel.
- */
- if (current_thread_info()->task->thread.used_vas)
- asm volatile(PPC_CP_ABORT);
- }
+ /*
+ * Math facilities are masked out of the child MSR in copy_thread.
+ * A new task does not need to restore_math because it will
+ * demand fault them.
+ */
+ if (current->thread.regs)
+ restore_math(current->thread.regs);
#endif /* CONFIG_PPC_BOOK3S_64 */
return last;
}
-static int instructions_to_print = 16;
+#define NR_INSN_TO_PRINT 16
static void show_instructions(struct pt_regs *regs)
{
int i;
- unsigned long pc = regs->nip - (instructions_to_print * 3 / 4 *
- sizeof(int));
+ unsigned long nip = regs->nip;
+ unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
printk("Instruction dump:");
- for (i = 0; i < instructions_to_print; i++) {
+ /*
+ * If we were executing with the MMU off for instructions, adjust pc
+ * rather than printing XXXXXXXX.
+ */
+ if (!IS_ENABLED(CONFIG_BOOKE) && !(regs->msr & MSR_IR)) {
+ pc = (unsigned long)phys_to_virt(pc);
+ nip = (unsigned long)phys_to_virt(regs->nip);
+ }
+
+ for (i = 0; i < NR_INSN_TO_PRINT; i++) {
int instr;
if (!(i % 8))
pr_cont("\n");
-#if !defined(CONFIG_BOOKE)
- /* If executing with the IMMU off, adjust pc rather
- * than print XXXXXXXX.
- */
- if (!(regs->msr & MSR_IR))
- pc = (unsigned long)phys_to_virt(pc);
-#endif
-
if (!__kernel_text_address(pc) ||
- probe_kernel_address((unsigned int __user *)pc, instr)) {
+ get_kernel_nofault(instr, (const void *)pc)) {
pr_cont("XXXXXXXX ");
} else {
- if (regs->nip == pc)
+ if (nip == pc)
pr_cont("<%08x> ", instr);
else
pr_cont("%08x ", instr);
@@ -1285,43 +1361,34 @@
void show_user_instructions(struct pt_regs *regs)
{
unsigned long pc;
- int i;
+ int n = NR_INSN_TO_PRINT;
+ struct seq_buf s;
+ char buf[96]; /* enough for 8 times 9 + 2 chars */
- pc = regs->nip - (instructions_to_print * 3 / 4 * sizeof(int));
+ pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
- /*
- * Make sure the NIP points at userspace, not kernel text/data or
- * elsewhere.
- */
- if (!__access_ok(pc, instructions_to_print * sizeof(int), USER_DS)) {
- pr_info("%s[%d]: Bad NIP, not dumping instructions.\n",
- current->comm, current->pid);
- return;
- }
+ seq_buf_init(&s, buf, sizeof(buf));
- pr_info("%s[%d]: code: ", current->comm, current->pid);
+ while (n) {
+ int i;
- for (i = 0; i < instructions_to_print; i++) {
- int instr;
+ seq_buf_clear(&s);
- if (!(i % 8) && (i > 0)) {
- pr_cont("\n");
- pr_info("%s[%d]: code: ", current->comm, current->pid);
+ for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
+ int instr;
+
+ if (copy_from_user_nofault(&instr, (void __user *)pc,
+ sizeof(instr))) {
+ seq_buf_printf(&s, "XXXXXXXX ");
+ continue;
+ }
+ seq_buf_printf(&s, regs->nip == pc ? "<%08x> " : "%08x ", instr);
}
- if (probe_kernel_address((unsigned int __user *)pc, instr)) {
- pr_cont("XXXXXXXX ");
- } else {
- if (regs->nip == pc)
- pr_cont("<%08x> ", instr);
- else
- pr_cont("%08x ", instr);
- }
-
- pc += sizeof(int);
+ if (!seq_buf_has_overflowed(&s))
+ pr_info("%s[%d]: code: %s\n", current->comm,
+ current->pid, s.buffer);
}
-
- pr_cont("\n");
}
struct regbit {
@@ -1429,14 +1496,15 @@
print_msr_bits(regs->msr);
pr_cont(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer);
trap = TRAP(regs);
- if ((TRAP(regs) != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
+ if (!trap_is_syscall(regs) && cpu_has_feature(CPU_FTR_CFAR))
pr_cont("CFAR: "REG" ", regs->orig_gpr3);
- if (trap == 0x200 || trap == 0x300 || trap == 0x600)
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
- pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
-#else
- pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
-#endif
+ if (trap == 0x200 || trap == 0x300 || trap == 0x600) {
+ if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+ pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+ else
+ pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
+ }
+
#ifdef CONFIG_PPC64
pr_cont("IRQMASK: %lx ", regs->softe);
#endif
@@ -1453,15 +1521,15 @@
break;
}
pr_cont("\n");
-#ifdef CONFIG_KALLSYMS
/*
* Lookup NIP late so we have the best change of getting the
* above info out without failing
*/
- printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
- printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
-#endif
- show_stack(current, (unsigned long *) regs->gpr[1]);
+ if (IS_ENABLED(CONFIG_KALLSYMS)) {
+ printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
+ printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
+ }
+ show_stack(current, (unsigned long *) regs->gpr[1], KERN_DEFAULT);
if (!user_mode(regs))
show_instructions(regs);
}
@@ -1475,26 +1543,14 @@
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
}
-int set_thread_uses_vas(void)
-{
#ifdef CONFIG_PPC_BOOK3S_64
- if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return -EINVAL;
-
- current->thread.used_vas = 1;
-
- /*
- * Even a process that has no foreign real address mapping can use
- * an unpaired COPY instruction (to no real effect). Issue CP_ABORT
- * to clear any pending COPY and prevent a covert channel.
- *
- * __switch_to() will issue CP_ABORT on future context switches.
- */
- asm volatile(PPC_CP_ABORT);
-
-#endif /* CONFIG_PPC_BOOK3S_64 */
- return 0;
+void arch_setup_new_exec(void)
+{
+ if (radix_enabled())
+ return;
+ hash__setup_new_exec();
}
+#endif
#ifdef CONFIG_PPC64
/**
@@ -1609,21 +1665,26 @@
* Copy architecture-specific thread state
*/
int copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long kthread_arg, struct task_struct *p)
+ unsigned long kthread_arg, struct task_struct *p,
+ unsigned long tls)
{
struct pt_regs *childregs, *kregs;
extern void ret_from_fork(void);
+ extern void ret_from_fork_scv(void);
extern void ret_from_kernel_thread(void);
void (*f)(void);
unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
struct thread_info *ti = task_thread_info(p);
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int i;
+#endif
- klp_init_thread_info(ti);
+ klp_init_thread_info(p);
/* Copy registers */
sp -= sizeof(struct pt_regs);
childregs = (struct pt_regs *) sp;
- if (unlikely(p->flags & PF_KTHREAD)) {
+ if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
/* kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
childregs->gpr[1] = sp + sizeof(struct pt_regs);
@@ -1646,17 +1707,20 @@
if (usp)
childregs->gpr[1] = usp;
p->thread.regs = childregs;
- childregs->gpr[3] = 0; /* Result from fork() */
+ /* 64s sets this in ret_from_fork */
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ childregs->gpr[3] = 0; /* Result from fork() */
if (clone_flags & CLONE_SETTLS) {
-#ifdef CONFIG_PPC64
if (!is_32bit_task())
- childregs->gpr[13] = childregs->gpr[6];
+ childregs->gpr[13] = tls;
else
-#endif
- childregs->gpr[2] = childregs->gpr[6];
+ childregs->gpr[2] = tls;
}
- f = ret_from_fork;
+ if (trap_is_scv(regs))
+ f = ret_from_fork_scv;
+ else
+ f = ret_from_fork;
}
childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX);
sp -= STACK_FRAME_OVERHEAD;
@@ -1675,11 +1739,11 @@
sp -= STACK_FRAME_OVERHEAD;
p->thread.ksp = sp;
#ifdef CONFIG_PPC32
- p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
- _ALIGN_UP(sizeof(struct thread_info), 16);
+ p->thread.ksp_limit = (unsigned long)end_of_stack(p);
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
- p->thread.ptrace_bps[0] = NULL;
+ for (i = 0; i < nr_wp_slots(); i++)
+ p->thread.ptrace_bps[i] = NULL;
#endif
p->thread.fp_save_area = NULL;
@@ -1695,13 +1759,15 @@
p->thread.dscr = mfspr(SPRN_DSCR);
}
if (cpu_has_feature(CPU_FTR_HAS_PPR))
- p->thread.ppr = INIT_PPR;
+ childregs->ppr = DEFAULT_PPR;
p->thread.tidr = 0;
#endif
kregs->nip = ppc_function_entry(f);
return 0;
}
+
+void preload_new_slb_context(unsigned long start, unsigned long sp);
/*
* Set up a thread for executing a new program
@@ -1710,6 +1776,9 @@
{
#ifdef CONFIG_PPC64
unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
+ preload_new_slb_context(start, sp);
#endif
/*
@@ -1731,7 +1800,7 @@
tm_reclaim_current(0);
#endif
- memset(regs->gpr, 0, sizeof(regs->gpr));
+ memset(®s->gpr[1], 0, sizeof(regs->gpr) - sizeof(regs->gpr[0]));
regs->ctr = 0;
regs->link = 0;
regs->xer = 0;
@@ -1743,7 +1812,7 @@
* FULL_REGS(regs) return true. This is necessary to allow
* ptrace to examine the thread immediately after exec.
*/
- regs->trap &= ~1UL;
+ SET_FULL_REGS(regs);
#ifdef CONFIG_PPC32
regs->mq = 0;
@@ -1800,6 +1869,7 @@
#ifdef CONFIG_VSX
current->thread.used_vsr = 0;
#endif
+ current->thread.load_slb = 0;
current->thread.load_fp = 0;
memset(¤t->thread.fp_state, 0, sizeof(current->thread.fp_state));
current->thread.fp_save_area = NULL;
@@ -1840,7 +1910,6 @@
* fpexc_mode. fpexc_mode is also used for setting FP exception
* mode (asyn, precise, disabled) for 'Classic' FP. */
if (val & PR_FP_EXC_SW_ENABLE) {
-#ifdef CONFIG_SPE
if (cpu_has_feature(CPU_FTR_SPE)) {
/*
* When the sticky exception bits are set
@@ -1854,16 +1923,15 @@
* anyway to restore the prctl settings from
* the saved environment.
*/
+#ifdef CONFIG_SPE
tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
tsk->thread.fpexc_mode = val &
(PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT);
+#endif
return 0;
} else {
return -EINVAL;
}
-#else
- return -EINVAL;
-#endif
}
/* on a CONFIG_SPE this does not hurt us. The bits that
@@ -1882,10 +1950,9 @@
int get_fpexc_mode(struct task_struct *tsk, unsigned long adr)
{
- unsigned int val;
+ unsigned int val = 0;
- if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE)
-#ifdef CONFIG_SPE
+ if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) {
if (cpu_has_feature(CPU_FTR_SPE)) {
/*
* When the sticky exception bits are set
@@ -1899,15 +1966,15 @@
* anyway to restore the prctl settings from
* the saved environment.
*/
+#ifdef CONFIG_SPE
tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
val = tsk->thread.fpexc_mode;
+#endif
} else
return -EINVAL;
-#else
- return -EINVAL;
-#endif
- else
+ } else {
val = __unpack_fe01(tsk->thread.fpexc_mode);
+ }
return put_user(val, (unsigned int __user *) adr);
}
@@ -1972,39 +2039,63 @@
unsigned long stack_page;
unsigned long cpu = task_cpu(p);
- /*
- * Avoid crashing if the stack has overflowed and corrupted
- * task_cpu(p), which is in the thread_info struct.
- */
- if (cpu < NR_CPUS && cpu_possible(cpu)) {
- stack_page = (unsigned long) hardirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
- return 1;
+ stack_page = (unsigned long)hardirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
- stack_page = (unsigned long) softirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
- return 1;
- }
+ stack_page = (unsigned long)softirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
return 0;
}
+
+static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
+ unsigned long nbytes)
+{
+#ifdef CONFIG_PPC64
+ unsigned long stack_page;
+ unsigned long cpu = task_cpu(p);
+
+ stack_page = (unsigned long)paca_ptrs[cpu]->emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+# ifdef CONFIG_PPC_BOOK3S_64
+ stack_page = (unsigned long)paca_ptrs[cpu]->nmi_emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ stack_page = (unsigned long)paca_ptrs[cpu]->mc_emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+# endif
+#endif
+
+ return 0;
+}
+
int validate_sp(unsigned long sp, struct task_struct *p,
unsigned long nbytes)
{
unsigned long stack_page = (unsigned long)task_stack_page(p);
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
+ if (sp < THREAD_SIZE)
+ return 0;
+
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
- return valid_irq_stack(sp, p, nbytes);
+ if (valid_irq_stack(sp, p, nbytes))
+ return 1;
+
+ return valid_emergency_stack(sp, p, nbytes);
}
EXPORT_SYMBOL(validate_sp);
-unsigned long get_wchan(struct task_struct *p)
+static unsigned long __get_wchan(struct task_struct *p)
{
unsigned long ip, sp;
int count = 0;
@@ -2017,12 +2108,12 @@
return 0;
do {
- sp = *(unsigned long *)sp;
+ sp = READ_ONCE_NOCHECK(*(unsigned long *)sp);
if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD) ||
p->state == TASK_RUNNING)
return 0;
if (count > 0) {
- ip = ((unsigned long *)sp)[STACK_FRAME_LR_SAVE];
+ ip = READ_ONCE_NOCHECK(((unsigned long *)sp)[STACK_FRAME_LR_SAVE]);
if (!in_sched_functions(ip))
return ip;
}
@@ -2030,47 +2121,61 @@
return 0;
}
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long ret;
+
+ if (!try_get_task_stack(p))
+ return 0;
+
+ ret = __get_wchan(p);
+
+ put_task_stack(p);
+
+ return ret;
+}
+
static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
-void show_stack(struct task_struct *tsk, unsigned long *stack)
+void show_stack(struct task_struct *tsk, unsigned long *stack,
+ const char *loglvl)
{
unsigned long sp, ip, lr, newsp;
int count = 0;
int firstframe = 1;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- int curr_frame = current->curr_ret_stack;
- extern void return_to_handler(void);
- unsigned long rth = (unsigned long)return_to_handler;
-#endif
+ unsigned long ret_addr;
+ int ftrace_idx = 0;
- sp = (unsigned long) stack;
if (tsk == NULL)
tsk = current;
+
+ if (!try_get_task_stack(tsk))
+ return;
+
+ sp = (unsigned long) stack;
if (sp == 0) {
if (tsk == current)
- sp = current_stack_pointer();
+ sp = current_stack_frame();
else
sp = tsk->thread.ksp;
}
lr = 0;
- printk("Call Trace:\n");
+ printk("%sCall Trace:\n", loglvl);
do {
if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD))
- return;
+ break;
stack = (unsigned long *) sp;
newsp = stack[0];
ip = stack[STACK_FRAME_LR_SAVE];
if (!firstframe || ip != lr) {
- printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- if ((ip == rth) && curr_frame >= 0) {
- pr_cont(" (%pS)",
- (void *)current->ret_stack[curr_frame].ret);
- curr_frame--;
- }
-#endif
+ printk("%s["REG"] ["REG"] %pS",
+ loglvl, sp, ip, (void *)ip);
+ ret_addr = ftrace_graph_ret_addr(current,
+ &ftrace_idx, ip, stack);
+ if (ret_addr != ip)
+ pr_cont(" (%pS)", (void *)ret_addr);
if (firstframe)
pr_cont(" (unreliable)");
pr_cont("\n");
@@ -2081,18 +2186,21 @@
* See if this is an exception frame.
* We look for the "regshere" marker in the current frame.
*/
- if (validate_sp(sp, tsk, STACK_INT_FRAME_SIZE)
+ if (validate_sp(sp, tsk, STACK_FRAME_WITH_PT_REGS)
&& stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
struct pt_regs *regs = (struct pt_regs *)
(sp + STACK_FRAME_OVERHEAD);
lr = regs->link;
- printk("--- interrupt: %lx at %pS\n LR = %pS\n",
- regs->trap, (void *)regs->nip, (void *)lr);
+ printk("%s--- interrupt: %lx at %pS\n LR = %pS\n",
+ loglvl, regs->trap,
+ (void *)regs->nip, (void *)lr);
firstframe = 1;
}
sp = newsp;
} while (count++ < kstack_depth_to_print);
+
+ put_task_stack(tsk);
}
#ifdef CONFIG_PPC64
--
Gitblit v1.6.2